diff mbox series

[PULL,27/34] target/ppc: Implement xxm[tf]acc and xxsetaccz

Message ID 20220526213815.92701-28-danielhb413@gmail.com (mailing list archive)
State New, archived
Headers show
Series [PULL,01/34] pseries: allow setting stdout-path even on machines with a VGA | expand

Commit Message

Daniel Henrique Barboza May 26, 2022, 9:38 p.m. UTC 
From: "Lucas Mateus Castro (alqotel)" <lucas.araujo@eldorado.org.br>

Implement the following PowerISA v3.1 instructions:
xxmfacc: VSX Move From Accumulator
xxmtacc: VSX Move To Accumulator
xxsetaccz: VSX Set Accumulator to Zero

The PowerISA 3.1 mentions that for the current version of the
architecture, "the hardware implementation provides the effect of ACC[i]
and VSRs 4*i to 4*i + 3 logically containing the same data" and "The
Accumulators introduce no new logical state at this time" (page 501).
For now it seems unnecessary to create new structures, so this patch
just uses ACC[i] as VSRs 4*i to 4*i+3 and therefore move to and from
accumulators are no-ops.

Signed-off-by: Lucas Mateus Castro (alqotel) <lucas.araujo@eldorado.org.br>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Message-Id: <20220524140537.27451-2-lucas.araujo@eldorado.org.br>
Signed-off-by: Daniel Henrique Barboza <danielhb413@gmail.com>
---
 target/ppc/cpu.h                    |  5 +++++
 target/ppc/insn32.decode            |  9 +++++++++
 target/ppc/translate/vsx-impl.c.inc | 31 +++++++++++++++++++++++++++++
 3 files changed, 45 insertions(+)
diff mbox series

Patch

diff --git a/target/ppc/cpu.h b/target/ppc/cpu.h
index bf8f8aad2c..c865206827 100644
--- a/target/ppc/cpu.h
+++ b/target/ppc/cpu.h
@@ -2663,6 +2663,11 @@  static inline int vsr_full_offset(int i)
     return offsetof(CPUPPCState, vsr[i].u64[0]);
 }
 
+static inline int acc_full_offset(int i)
+{
+    return vsr_full_offset(i * 4);
+}
+
 static inline int fpr_offset(int i)
 {
     return vsr64_offset(i, true);
diff --git a/target/ppc/insn32.decode b/target/ppc/insn32.decode
index f001c02a8c..c0f545ca38 100644
--- a/target/ppc/insn32.decode
+++ b/target/ppc/insn32.decode
@@ -154,6 +154,9 @@ 
 &X_vrt_frbp     vrt frbp
 @X_vrt_frbp     ...... vrt:5 ..... ....0 .......... .           &X_vrt_frbp frbp=%x_frbp
 
+&X_a            ra
+@X_a            ...... ra:3 .. ..... ..... .......... .         &X_a
+
 %xx_xt          0:1 21:5
 %xx_xb          1:1 11:5
 %xx_xa          2:1 16:5
@@ -734,3 +737,9 @@  XVTLSBB         111100 ... -- 00010 ..... 111011011 . - @XX2_bf_xb
 &XL_s           s:uint8_t
 @XL_s           ......-------------- s:1 .......... -   &XL_s
 RFEBB           010011-------------- .   0010010010 -   @XL_s
+
+## Accumulator Instructions
+
+XXMFACC         011111 ... -- 00000 ----- 0010110001 -   @X_a
+XXMTACC         011111 ... -- 00001 ----- 0010110001 -   @X_a
+XXSETACCZ       011111 ... -- 00011 ----- 0010110001 -   @X_a
diff --git a/target/ppc/translate/vsx-impl.c.inc b/target/ppc/translate/vsx-impl.c.inc
index 900c1a1ab2..235be360e2 100644
--- a/target/ppc/translate/vsx-impl.c.inc
+++ b/target/ppc/translate/vsx-impl.c.inc
@@ -2816,6 +2816,37 @@  static bool trans_XVCVBF16SPN(DisasContext *ctx, arg_XX2 *a)
     return true;
 }
 
+    /*
+     *  The PowerISA 3.1 mentions that for the current version of the
+     *  architecture, "the hardware implementation provides the effect of
+     *  ACC[i] and VSRs 4*i to 4*i + 3 logically containing the same data"
+     *  and "The Accumulators introduce no new logical state at this time"
+     *  (page 501). For now it seems unnecessary to create new structures,
+     *  so ACC[i] is the same as VSRs 4*i to 4*i+3 and therefore
+     *  move to and from accumulators are no-ops.
+     */
+static bool trans_XXMFACC(DisasContext *ctx, arg_X_a *a)
+{
+    REQUIRE_INSNS_FLAGS2(ctx, ISA310);
+    REQUIRE_VSX(ctx);
+    return true;
+}
+
+static bool trans_XXMTACC(DisasContext *ctx, arg_X_a *a)
+{
+    REQUIRE_INSNS_FLAGS2(ctx, ISA310);
+    REQUIRE_VSX(ctx);
+    return true;
+}
+
+static bool trans_XXSETACCZ(DisasContext *ctx, arg_X_a *a)
+{
+    REQUIRE_INSNS_FLAGS2(ctx, ISA310);
+    REQUIRE_VSX(ctx);
+    tcg_gen_gvec_dup_imm(MO_64, acc_full_offset(a->ra), 64, 64, 0);
+    return true;
+}
+
 #undef GEN_XX2FORM
 #undef GEN_XX3FORM
 #undef GEN_XX2IFORM